Respond AI: AI Agent - Process images from incoming messages
in progress
W
Wilson Tan
Business problem:
Currently, AI Agent does not have the capability to process images from messages. This feature would help platform users handle objective queries where the contact sends an image, AI Agent will not be able to process it answer based on the image that the contact is enquiring about.
Desired outcome:
Allow AI to process images based on the image from messages. Specific use cases:
- Identify brands of items of the image and provide a response on said brand / product
- Identify issues from images and provide a response based on knowledge sources (i.e. image of a malfunctioning device of a specific brand)
- Process an image of a form, receipt, etc
Use case (Capture, Convert, Retain):
This feature spans multiple phases:
- Capture: Visually engage users early in the journey—think visual search or product discovery via images.
- Convert: Streamline image-based product matching and upselling in chat.
- Retain: Use visual input to reduce back-and-forth and solve problems faster.
N
Nabilah Binti Salleh
Merged in a post:
AI Agent: Capability to respond to messages containing images with captions.
Viiky Ng
Business Problem:
Currently, when the AI agent is tasked with responding to contact inquiries, it overlooks messages presented as an image accompanied by a caption within a single block.
Desired Outcome:
The objective is for the AI agent to effectively handle and respond to messages that consist of images combined with captions, thereby avoiding the redirection of such conversations to the IDLE journey.
N
Nabilah Binti Salleh
in progress
J
Janina Kotze
Voted - yes at the very least AI Data Collection Agent should be able to receive an image or file and save it to a variable. There is no need to recognize or read the content of the image, just receive it and move on to the next action. It is currently stuck.
S
Shi Hui
planned
Y
Yihui Chan
Merged in a post:
Agent AI will be able to receive images
L
Luis Araujo
The AI Data Collection Agent should be able to at least receive an image or file and save it to a variable. There is no need to recognize or read the content of the image, just receive it and move on to the next action. It is currently stuck.
Jean Paul Carbajal
I voted for the feature request on your behalf, this will help us launch the feature faster and you'll receive a notification when it's ready 💪